论文

本文提出通过熵正则化对 Wasserstein 距离进行平滑处理，由此得到一个严格凸的目标函数，其梯度可借助矩阵缩放算法以显著更低的计算代价求得。The Wasserstein distance is proposed to be smoothed with an entropic regularizer and recover in doing so a strictly convex objective whose gradients can be computed for a considerably cheaper computational cost using matrix scaling algorithms.

所提出的通用度量空间搜索索引显著优于此前开源的 SOTA 纯向量方法，且该算法与 skip list 结构的相似性便于直接实现均衡的分布式部署。The proposed general metric space search index is able to strongly outperform previous opensource state-of-the-art vector-only approaches and similarity of the algorithm to the skip list structure allows straightforward balanced distributed implementation.

提出一个模型，基于图像区域上的 CNN、句子上的双向 RNN 以及通过多模态嵌入对齐两种模态的结构化目标，生成图像及其区域的自然语言描述。A model that generates natural language descriptions of images and their regions based on a novel combination of Convolutional Neural Networks over image regions, bidirectional Recurrent Neural Networks over sentences, and a structured objective that aligns the two modalities through a multimodal embedding is presented.

提出 Manhattan NMF（MahNMF），通过最小化 $X$ 与 $W^T H$ 之间的 Manhattan 距离建模重尾 Laplacian 噪声，并以迭代方式提升 MahNMF 及其扩展的近似精度。Manhattan NMF (MahNMF) is presented which minimizes the Manhattan distance between $X and $W^T H$ for modeling the heavy tailed Laplacian noise and improves the approximation accuracy iteratively for both MahNMF and its extensions.

总结了利用人工智能以及语音与语言处理预测阿尔茨海默病相关认知衰退的现有研究发现。The existing findings on the use of artificial intelligence, speech, and language processing to predict cognitive decline in the context of Alzheimer’s disease are summarized.

本文介绍 Gemma，一族基于 Gemini 模型所使用的研究与技术构建的轻量级 SOTA 开源模型，并全面评估模型的安全性与责任性，同时详细描述模型开发过程。This work introduces Gemma, a family of lightweight, state-of-the art open models built from the research and technology used to create Gemini models, and presents comprehensive evaluations of safety and responsibility aspects of the models, alongside a detailed description of model development.

提出一种全可微、样本级影响力估计器，可在不进行耗时的逆 Hessian 乘积或凸性假设的前提下，量化因添加或移除数据而产生的参数变化。A fully differentiable, sample-level influence estimator that quantifies parameter shifts from adding or removing data, without time-consuming inverse-Hessian products or convexity assumptions is introduced.

本实证研究通过建模数据组成对计算定律及分配指数的影响，推导出指定模型规模、token 数和数据混合精确配置的效率前沿，为可预测地扩展多模态基础模型奠定了必要基础。This empirical research establishes the essential groundwork for predictably scaling multimodal foundation models by modeling the influence of data composition on compute laws and allocation exponents and derive an efficiency frontier specifying precise configurations of model size, token count, and data mixture.

该工作主张将研究构想视为多目标的联合问题，并将其建模为 Quality-Diversity (QD) 搜索；同时提出 IDEAgent，一个通过 lineage 管理思路演化的 multi-agent 框架。This work argues that research ideation should be treated as a conjunction of both objectives and framed as a Quality-Diversity (QD) search, and introduces IDEAgent, a multi-agent framework that manages the evolution of ideas through lineages.

该工作发布了 LAMAR，一种具备语言感知能力的多语种 cross encoder，在训练中兼顾语义相关性与语言连贯性，在通用多语种 reranking 基准上整体以及各语言单独评估中均达到最佳性能。This work releases LAMAR, a language aware multilingual cross encoder trained to account for both semantic relevance and language coherence, which achieves the best performance overall and across all languages examined individually on general multilingual reranking benchmarks.

Molt 是一个 PyTorch-native 的训练框架，旨在压低上述开销：代码库精简清晰，研究者能完整装进脑中，AI 编程助手也能完整阅读和推理，从而可以端到端地追溯和修改算法流程。Molt is a PyTorch-native training framework built to keep that cost small: a codebase compact and clean enough for a researcher to hold in their head, and for an AI coding assistant to read and reason about in its entirety, so the algorithm flow can be traced and changed end to end.

VisCo 是一个训练高效的自压缩框架，复用预训练 VLM 本身作为内在压缩器，使用少量 memory token 压缩视觉信息，并将层次化信息从编码传递到解码。VisCo is a training-efficient self-compression framework that reuses the pretrained VLM itself as an intrinsic compressor that compresses visual information using a small set of memory tokens and transfers hierarchical information from encoding to decoding.

提出 Spectral Alignment，一种基于 guidance 的轻量级方法，将中间预测的功率谱校准到预先计算的先验，并与 Classifier-Free Guidance (CFG) 互补。Spectral Alignment is proposed, a lightweight, guidance-based method that calibrates the power spectrum of intermediate predictions to a pre-computed prior and is complementary to Classifier-Free Guidance (CFG).

该工作在多语句、多模态设定下研究 ASV，考察跨匿名语音聚合信息是否影响隐私，并发现帧级聚合得到的 EER 最低。This work investigates ASV in a multi-utterance, multimodal setting and examines whether aggregating information across anonymized speech impacts privacy, and finds that frame-level aggregation yields the lowest EERs.

这些结果将 tracked scattering 确立为通往高维 one-step generation 的路径，并给出一张设计图，将 diffusion 相关监督、Drift-like 动力学与 GAN-like 目标联系起来。These results establish tracked scattering as a route to high-dimensional one-step generation and provide a design map relating diffusion-related supervision, Drift-like dynamics, and GAN-like objectives.

该工作提出一个面向异常检测的免训练 agentic 框架，无需领域特定知识，旨在追踪被检测对象随时间变化的空间-时间动态与底层变换，然后基于逐对象的时间状态轨迹进行推理，在 grounding 帧中识别异常对象。This work introduces a training-free agentic framework for anomaly detection free of domain-specific knowledge, designed to track spatial-temporal dynamics and underlying transformations of detected objects over time, and then reason over the object-wise temporal state trajectories to identify abnormal objects in grounded frames.

DeCoRAG 是一个多模态 Graph RAG pipeline，将知识处理从耦合的视觉-语义推理转向认知层面的 Decoupling，进而把推理空间从稠密、带噪的背景推向纯净、意图驱动的语义簇。DeCoRAG is a multimodal Graph RAG pipeline that shifts knowledge processing from coupled visual-semantic reasoning to cognitive Decoupling, and subsequently drives the reasoning space from dense, noisy backgrounds to purified, intent-driven semantic clusters.

本文提出一个半符号化框架，将用于 OCR 后校正的 word-spotting 技术与知识图谱表示相结合，使 agent 可通过合成查询访问信息，从而对误读和幻觉具有鲁棒性。This paper introduces a semi-symbolic framework that integrates word-spotting techniques for post-OCR correction with a knowledge graph representation that enables the agent to access information through synthesized queries that are robust to misinterpretation and hallucination.

提出一个统一且受控的多轮环境，可在三阶段精确控制长程规划；研究表明，多教师 on-policy 蒸馏 (MOPD) 通过收敛到跨环境共享的规划模式来整合多种能力。A unified and controlled multi-turn environment that enables precise control of long-horizon planning across three stages is introduced and it is shown that multi-teacher on-policy distillation (MOPD) integrates capabilities by converging to shared planning-pattern across environments.

提出一种面向历史文档修复的新框架，利用搭载 RAG 的大语言模型，有效缓解了推断上下文相关专有名词的难题。A novel framework for historical document restoration that leverages large language models with retrieval-augmented generation (RAG) and effectively mitigates the challenge of inferring context-dependent proper nouns is introduced.

本文提出无需训练的 Sol-Attn（Sparsifying online attention），在单次 online-softmax pass 中统一动态路由、稀疏计算与近似修正，在稀疏注意力中取得更好的精度–效率权衡。This paper introduces training-free Sol-Attn (Sparsifying online attention), which unifies dynamic routing, sparse computation, and approximation correction in a single online-softmax pass, achieving a better accuracy-efficiency trade-off in sparse attention.

本文提出 Chamaileon，通过将问题建模为跨上下文结合景观（cross-context binding landscape modeling），统一多目标与多态 binder 设计，有效生成可适配多样构象景观与多目标需求的序列。Chamaileon is introduced, which unifies multi-target and multi-state binder design by formulating the problem as cross-context binding landscape modeling and effectively generates sequences adaptable to diverse conformational landscapes and multi-target requirements.

RedE 利用 final-answer attention 作为自动监督信号来塑造 step-level 表征空间，使其中的噪声步骤可被可靠识别与过滤，并在检测性能上超越有竞争力的基线。RedE leverages final-answer attention as an automatic supervision signal to shape the step-level representation space, yielding refined embeddings in which noisy steps can be reliably identified and filtered and improves detection performance over competitive baselines.

本文提出 PAJAMA，该系统将程序合成为 judge，将其决策聚合为联合裁决（joint verdict），并通过 fallback 机制选择性地将低置信度用例升级交由 LLM 处理。PAJAMA is introduced, a system that synthesizes programs as judges, aggregates their decisions into a joint verdict, and incorporates a fallback mechanism to selectively escalate low-confidence cases to an LLM.

WorldDiT 是一种统一的 diffusion Transformer 架构，将动作生成与视觉世界建模耦合，无需大型预训练 VLM 动作主干即取得强性能，在报告全部四个 suite 的方法中，其总模型参数量与平均成功率处于已报告的 Pareto 前沿上。WorldDiT, a unified diffusion transformer architecture that couples action generation with visual world modeling and achieves strong performance without a large pretrained VLM action backbone, lies on the reported Pareto frontier for total model parameters and mean success among methods reporting all four suites.

本文提出一种面向由一个或多个 agent 构建的自动化研究系统的词汇表，使其设计选择更易于描述与比较，从而将结构性设计问题——例如 agent 应在何时通信、获得或失去某项能力，或在多次运行间传递信息——转化为可测试的选择。A vocabulary for automated research systems built from one or more agents to make their design choices easier to describe and compare, which turns structural design questions, such as when agents should communicate, gain or lose a capability, or carry information across runs, into testable choices.

本文发现视觉提示工程（visual prompt engineering，简称 VIPE）能在多项任务上提升视频推理性能，甚至比经典的文本提示工程或 test-time scaling 更有效。It is found that visual prompt engineering, or VIPE for short, improves video reasoning performance across tasks and can be even more effective than classic text-based prompt engineering or test-time scaling.

本文在由专家级 MITRE Center for Threat-Informed Defense 标注构成的、包含 1,207 条 CVE 的精选 gold 数据集上训练多标签分类器，结果表明该分类器受限于标签质量而非数据规模。A multi-label classifier is trained on a curated gold dataset of 1,207 CVEs from expert MITRE Center for Threat-Informed Defense mappings, indicating that the classifier is limited by label quality rather than dataset size.

本文提出 RARG（Relevance-Aware RipGrep Search Agent），将相关性转化为 corpus 交互的执行先验，并证明相关性感知交互可带来更快且更可靠的搜索收敛。The Relevance-Aware RipGrep Search Agent (RARG) is introduced, which turns relevance into an execution prior for corpus interaction, and demonstrates that relevance-aware interaction enables faster and more reliable search convergence.

本文提出 Mage-VL，一种面向实时多模态理解与交互的高效 codec-native 流式基础模型，并构建了 AI4AI 数据流水线，涵盖面向多模态 captioning 的 prompt-code 联合优化与以 AI 驱动的性能诊断，以指导训练方案。Mage-VL is presented, an efficient codec-native streaming foundation model for real-time multimodal understanding and interaction and establishes AI4AI data pipelines encompassing prompt-code joint optimization for multimodal captioning and AI-driven performance diagnosis to guide training recipes.

本文综述了该边界上的五类漏洞：多步攻击链、与沙箱边界冲突的目标、供应链与凭据暴露、持续性的 command-and-control，以及自动化行动的速度。This review synthesizes five vulnerability classes at that boundary: multi-step offensive chains, objectives that conflict with sandbox boundaries, supply-chain and credential exposure, persistent command-and-control, and the speed of automated action.

本文提出 Kontrast，一种利用 Text-to-SPARQL 与 LLM 推理将基于表格的答案与 KG 证据进行对比并对所产生的不一致性进行分类的自动框架，并表明文本、表格与 KG 可通过系统性对比相互补充与纠错。Kontrast is presented, an automatic framework that uses Text-to-SPARQL and LLM reasoning to compare table-based answers with KG evidence and categorize the resulting inconsistencies, and shows that text, tables, and KGs can complement and correct one another through systematic comparison.

BeyondUncertainty 首先引出结构化的临时答案与置信度估计，然后应用在 held-out 验证数据上选定并在测试评估前冻结的模型特定阈值，揭示了更具选择性的证据获取与端到端 token 效率之间的权衡。BeyondUncertainty first elicits a structured provisional answer and confidence estimate, then applies a model-specific threshold selected on held-out validation data and frozen before test evaluation, revealing a trade-off between more selective evidence acquisition and end-to-end token efficiency.

这些结果共同支持多视角的仓库上下文服务，在仓库上下文全生命周期中提供显式的、面向操作的有效性边界以及质量-成本前沿。Together, these results support multi-view repository-context serving with explicit, operation-specific validity boundaries with quality-cost frontiers across the repository-context lifecycle.

介绍 Parallel Decoding Distillation，一种简化且可扩展的基于轨迹的蒸馏方法，用于 diffusion 和 flow matching 模型的快速推理，并显著提升生成视频的多样性。Parallel Decoding Distillation is introduced, a simplified and scalable trajectory-based distillation method for fast inference of diffusion and flow matching models and presents a significant improvement in generated video diversity.

介绍 VisualPatchWorld，将世界动态表示为代码，先通过短时主动探查选择定性动力学形式，再通过最小化多步预测误差，从记录的状态-动作轨迹中拟合该形式的自由参数。VisualPatchWorld is introduced, which represents world dynamics as code and first selects a qualitative dynamical form with short active probes, then fits that form's free parameters from recorded state-action traces by minimizing multi-step prediction error.